Shift Invariance Can Reduce Adversarial Robustness

3 March 2021

Papers citing "Shift Invariance Can Reduce Adversarial Robustness"

7 / 7 papers shown

Title
Training Image Derivatives: Increased Accuracy and Universal Robustness V. Avrutskiy 36 0 0 21 Oct 2023
Alias-Free Convnets: Fractional Shift Invariance via Polynomial Activations H. Michaeli T. Michaeli Daniel Soudry 21 14 0 14 Mar 2023
On the Limitations of Stochastic Pre-processing Defenses Yue Gao Ilia Shumailov Kassem Fawaz Nicolas Papernot AAML SILM 34 30 0 19 Jun 2022
Adversarial Robustness Comparison of Vision Transformer and MLP-Mixer to CNNs Philipp Benz Soomin Ham Chaoning Zhang Adil Karjauv In So Kweon AAML ViT 36 78 0 06 Oct 2021
Low Curvature Activations Reduce Overfitting in Adversarial Training Vasu Singla Sahil Singla David Jacobs S. Feizi AAML 32 45 0 15 Feb 2021
Towards Learning Convolutions from Scratch Behnam Neyshabur SSL 220 71 0 27 Jul 2020
On Translation Invariance in CNNs: Convolutional Layers can Exploit Absolute Spatial Location O. Kayhan J. C. V. Gemert 209 232 0 16 Mar 2020